The role of artificial intelligence in sarcopenia: Advances, applications, and future directions.
Authors
Affiliations (4)
Affiliations (4)
- Cadet College Kohat, Togh Payan, Kohat 26000, Pakistan.
- Beaconhouse International College, H-11/4, Islamabad 44000, Pakistan.
- Informatics Complex, H-8/1, Street 1, Islamabad 46000, Pakistan.
- Basic Medical Sciences, College of Medicine, University of Sharjah, Sharjah, United Arab Emirates; Cardiovascular Research Group, Sharjah Institute for Medical and Health Sciences, University of Sharjah, Sharjah 27272, United Arab Emirates; Space Medicine Research Group, Sharjah Institute for Medical and Health Sciences, University of Sharjah, Sharjah 27272, United Arab Emirates. Electronic address: [email protected].
Abstract
Sarcopenia, the gradual loss of skeletal muscle mass, strength, and function, is a growing concern in aging populations. Early detection is vital to reduce the risk of frailty, disability, and mortality, yet traditional diagnostic methods such as imaging and physical performance tests are often costly, inconsistent, or difficult to implement in routine care. Artificial intelligence (AI), including machine learning (ML) and deep learning (DL), is emerging as a powerful tool in sarcopenia research and clinical practice. This review explores how AI is being applied to early detection, imaging-based diagnosis, prediction of functional outcomes, and personalized monitoring. Models trained on large datasets, such as NHANES, have demonstrated strong predictive performance using standard clinical variables. DL has enabled automated analysis of CT scans for muscle segmentation, reducing the need for manual interpretation. At the same time, ML systems integrated with wearable devices allow real-time tracking of physical function. Emerging approaches such as explainable AI, federated learning, and the integration of diverse data sources, including omics and microbiome profiles, are expanding opportunities for individualized care. Despite these advances, significant challenges remain, including variability in data quality, limited model transparency, algorithmic bias, and ethical concerns. Regulatory oversight and clinician engagement will be key to successful implementation. AI offers a promising path toward proactive, scalable, and personalized management of sarcopenia.